Training networks in null space of feature covariance for continual learning

S Wang, X Li, J Sun, Z Xu - … of the IEEE/CVF conference on …, 2021 - openaccess.thecvf.com
In the setting of continual learning, a network is trained on a sequence of tasks, and suffers
from catastrophic forgetting. To balance plasticity and stability of network in continual …

[PDF][PDF] Training Networks in Null Space of Feature Covariance for Continual Learning

S Wang, X Li, J Sun, Z Xu - openaccess.thecvf.com
In the setting of continual learning, a network is trained on a sequence of tasks, and suffers
from catastrophic forgetting. To balance plasticity and stability of network in continual …

Training Networks in Null Space of Feature Covariance for Continual Learning

S Wang, X Li, J Sun, Z Xu - arXiv preprint arXiv:2103.07113, 2021 - arxiv.org
In the setting of continual learning, a network is trained on a sequence of tasks, and suffers
from catastrophic forgetting. To balance plasticity and stability of network in continual …

Training Networks in Null Space of Feature Covariance for Continual Learning

S Wang, X Li, J Sun, Z Xu - 2021 IEEE/CVF Conference on Computer …, 2021 - computer.org
In the setting of continual learning, a network is trained on a sequence of tasks, and suffers
from catastrophic forgetting. To balance plasticity and stability of network in continual …

Training Networks in Null Space of Feature Covariance for Continual Learning

S Wang, X Li, J Sun, Z Xu - arXiv e-prints, 2021 - ui.adsabs.harvard.edu
In the setting of continual learning, a network is trained on a sequence of tasks, and suffers
from catastrophic forgetting. To balance plasticity and stability of network in continual …

Training Networks in Null Space of Feature Covariance for Continual Learning

S Wang, X Li, J Sun, Z Xu - 2021 IEEE/CVF Conference on …, 2021 - ieeexplore.ieee.org
In the setting of continual learning, a network is trained on a sequence of tasks, and suffers
from catastrophic forgetting. To balance plasticity and stability of network in continual …